International Journal of Business Analytics and Intelligence

Riktesh Srivastava ¹

Affiliations
1 Information Systems, Skyline University College, Sharjah, AE

Abstract

Competitive world today stresses of having virtuous marketing strategies to appeal new customers while holding longstanding customers. Organisations use instruments to embrace both types of customers, thereby, probing better return on investments and ensuing increasing revenues. The notion of "customer clustering" is used by organisations to categorise diverse fragments of customers and offer them with varied services. The present study takes the four fragments of customers, viz., active, warm, cold, and inactive and does added exploration of these fragments. It was found that these fragments are not enough for defining marketing strategies and need further analysis. The paper magnifies the fragment using RFM analysis then performing clustering on the values obtained from this analysis. This analysis spawns the pertinent rules for each customer segment obtained after clustering.

Keywords

RFM, Customer Value Pyramid (CVP), Customer Clusters, Clustering without Classification, Clustering with Classification.

Full Text

     

Riktesh Srivastava ¹

Affiliations
1 Information Systems, Skyline University College, Sharjah, AE

Abstract

Indian B2C electronic commerce market is rising at an aggressive pace of 21.3% and is likely to reach $28 billion revenue by 2019-2020 with annual growth rate of 45% in next 4 years. Also, the electronic commerce contributes 1.23% of the consolidated 7.6% GDP of India. The electronic commerce progression rate for India is expected to be 31.2%, as compared to 9.9% and 8.3% for China and Australia, respectively during 2016-2021. Also, B2C electronic commerce industry in India is the fastest growing industry, as matched to other industries, and has reached $38 billion market value in 2016, a jump of 67% from 2015. Also with mobile shopping further maturing and consumer mindshare continuing to split across multiple devices, these companies struggle to align consumer interactions with business strategies. It is due to this reason, they use social media for better consumer interactions and spreading brand awareness digitally. It is presumed that social media has the ability to increase sales because of their strong online presence. Also, when these companies communicate with consumers through social media networks, they are able to get feedback instantly, which gives them quick acumen into what they want. The current study focuses on an analysis of these feedbacks collected by top 5 B2C electronic companies in India, namely, Amazon India, Flipkart, Snapdeal, Myntra, and eBay India. The feedback analysis is conducted based on the tweets from these companies on Twitter for 3 months, from 01-01-2017 to 31-03-2017. The experiment is conducted using Naïve Bayes Algorithm for 1500 tweets and places the response into one of the quadrants on proposed investigation model called "4AIM" - 4A Investigation Model. Based on the outcomes, the study adopts the generic social media strategies (BWDC, 2014), which these companies can embrace and implement accordingly.

Keywords

Electronic Commerce, Naïve Bayes Algorithm, 4AIM, Amazon India, Flipkart, Snapdeal, Myntra, eBay India, Social Media Strategies.

Full Text

     

Riktesh Srivastava ¹

Affiliations
1 City University College of Ajman, Ajman, AE

Abstract

Sentiment analysis is one of the vital areas to evaluate customer emotions. The growing prominence of sentiment analysis is because of social network platforms, which companies use for 360-degree consumer feedback. Companies use sentiment analysis as an automated process of recognising positive and negative emotions in online text data. By examining sentiments in social media comments and reviews, businesses can better understand how customers feel about their brands and products. Visual sentiment analysis aims to understand how images affect people in terms of evoked emotions. Companies are exposed to consumers’ images on social media by consumers, and they need image analytics for social listening and response. In this paper, we took 21 random pictures from social media to identify the visual sentiment analysis. We use the image embedding algorithm in Inception V3, and Liu Hu and Ekman Algorithm to calculate the outcomes’ polarity. Further, we used the machine learning classification algorithm to identify which model does the accurate classification of evoked emotions as happy and sad. Classification algorithms are based on the 2,048 features generated by the Inception V3 algorithm, and evoked emotions are classified accordingly.

Keywords

Inception V3, Liu Hu Algorithm, Ekman Polarity, Image Analytics, Picture Polarity, Naïve Bayes, Support Vector Machine, Neural Networks, Random Forest.

Full Text